The Community for Technology Leaders
Green Image
<p>The authors present the Meta-Pi network, a multinetwork connectionist classifier that forms distributed low-level knowledge representations for robust pattern recognition, given random feature vectors generated by multiple statistically distinct sources. They illustrate how the Meta-Pi paradigm implements an adaptive Bayesian maximum a posteriori classifier. They also demonstrate its performance in the context of multispeaker phoneme recognition in which the Meta-Pi superstructure combines speaker-dependent time-delay neural network (TDNN) modules to perform multispeaker /b,d,g/ phoneme recognition with speaker-dependent error rates of 2%. Finally, the authors apply the Meta-Pi architecture to a limited source-independent recognition task, illustrating its discrimination of a novel source. They demonstrate that it can adapt to the novel source (speaker), given five adaptation examples of each of the three phonemes.</p>
speech recognition; Meta-Pi network; distributed knowledge representations; multisource pattern recognition; multinetwork connectionist classifier; adaptive Bayesian maximum a posteriori classifier; multispeaker phoneme recognition; speaker-dependent time-delay neural network; Bayes methods; knowledge representation; neural nets; speech recognition; statistical analysis

A. Waibel and J. Hampshire II, "The Meta-Pi Network: Building Distributed Knowledge Representations for Robust Multisource Pattern Recognition," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 14, no. , pp. 751-769, 1992.
99 ms
(Ver 3.3 (11022016))